A human resource optimization configuration system based on talent assessment

Abstract

The present invention discloses a human resource optimization configuration system based on talent assessment, and the present invention relates to the field of human resource technology. The human resource optimization configuration system based on talent assessment includes a server, a processing unit and a client, and can perform multi-dimensional and multi-mode data collection for different types of enterprises, and can realize time series data accumulation, realize data storage and migration for large-scale structured and unstructured data, and combine the Johari theory in the field of human resource organization management with intelligent analysis and statistical machine learning to perform data analysis modeling, and finally realize configurable data visualization charts, data statistical learning reports and capability assessment reports of different granularities.

Description

Technical Field

[0001] The present invention relates to the technical field of human resources, and in particular to a human resources optimization configuration system based on talent evaluation. Background Art

[0002] Human resource allocation refers to the scientific and reasonable allocation of human resources in a specific organization or enterprise in order to improve work efficiency and optimize human resources. The purpose of human resource management is to make the best use of talents, personnel and work, and maximize the role of human resources. Talent assessment methods refer to the activities of measuring and evaluating people's basic qualities and performance through a series of scientific means and methods. The specific object of talent assessment methods is not an abstract person, but the inherent qualities of people as individuals and their performance.

[0003] The invention with publication number CN116629814A discloses a human resource optimization configuration system based on talent assessment. By mixing specific work tasks for assessment into daily work tasks, comparative analysis and evaluation are performed through preset specific task models to obtain work element feature assessment conclusions and work element feature configuration suggestions for the assessed person.

[0004] As shown in the above invention, the existing human resource optimization configuration system obtains the decision maker's characteristic attribute requirements for the work task, obtains a preliminary list of staff who meet the characteristic attribute requirements of the work task from the feature database, and screens and outputs the staff configuration list based on the work element feature evaluation conclusions and work element feature configuration suggestions of each staff member in the preliminary staff list. While fully avoiding factors such as the evaluated person guessing the evaluator's intentions and avoiding the decision being influenced by subjective factors, it can quickly and conveniently provide a list of staff suitable for the work task to assist decision makers in analysis and decision-making.

[0005] However, the more the existing job quality requirements are consistent with the qualities of the job incumbent, the better the performance and job satisfaction will be. The difficulty of competency evaluation lies in the high quality requirements of the evaluator, the need for professionals, the complex operation, the large workload, the high evaluation cost, and the inability to meet people's usage needs. Summary of the invention

[0006] In view of the deficiencies of the prior art, the present invention provides a human resource optimization configuration system based on talent evaluation, which solves the existing problems.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: a human resources optimization configuration system based on talent assessment, including a server, a processing unit and a client;

[0008] The server is configured as a platform for managing enterprise user accounts, assessment activity reports and data storage;

[0009] The processing unit includes a data acquisition module, a data management module, a data analysis module, an evaluation unit, a display module, a feature extraction module and a feature database;

[0010] The client serves as a platform for information interaction between users and the system, and mainly includes an account login module and a data upload module.

[0011] Preferably, the server includes enterprise user login, system maintenance, evaluation report generation, user information maintenance and historical data storage.

[0012] Preferably, the data acquisition module is used to acquire data uploaded by customers and user public data downloaded by the big data center;

[0013] The evaluation unit is used to generate test questions and test papers and evaluate the results;

[0014] The data management module is used to collect employee information in multiple dimensions based on the basic information uploaded by the user, the public data downloaded by the big data center, and the evaluation result data, so as to obtain multi-dimensional collected data of enterprise employees;

[0015] The data analysis module performs cluster analysis, classification analysis and outlier analysis on the multi-dimensional collected data of the enterprise employees based on machine learning technology to obtain data analysis results;

[0016] The display module generates configurable data visualization charts, visualization analysis reports and capability assessment reports, and visually displays the data visualization charts, visualization analysis reports and capability assessment reports;

[0017] The feature extraction module is used to extract the identity information of the person being evaluated and the associated work element features;

[0018] The feature database is used to store user feature data.

[0019] Preferably, the evaluation unit includes a question bank maintenance module, a question classification module, a question import module and a test paper evaluation module.

[0020] Preferably, the question bank maintenance module is used to query the question category, question source, question difficulty information, add and modify question description (single choice, multiple choice, short answer), question classification, answer, question difficulty, question status (enabled, disabled), question category information

[0021] The test question classification module is used to classify the test questions in the test question bank according to the user's position, combine the examination direction of the questions in the test question bank, and automatically generate the evaluation test paper according to the test question composition strategy;

[0022] The test question importing module is used to import the assessment test papers into the system;

[0023] The test paper evaluation module uses a big data analysis engine to perform relevant operations on statistical indicators based on the test paper composition strategy, generates a statistical report based on the calculation results, and generates corresponding suggestions.

[0024] Preferably, the system further comprises a log module for generating a work log, wherein the work log at least comprises progress dates, processing contents corresponding to each date, problems encountered and planned solutions.

[0025] Preferably, a log filling module is provided in the log module, and the work log filling module includes a progress date selection module, a processing content filling module, a problem to be solved filling module and a planned solution filling module.

[0026] Preferably, the system further comprises a warning reminder module for providing a reminder notification when the evaluation unit cannot be started or cannot perform comparative analysis on the key information extracted by the feature extraction module.

[0027] Beneficial Effects

[0028] The present invention provides a human resources optimization configuration system based on talent assessment. Compared with the prior art, it has the following beneficial effects:

[0029] 1. This human resource optimization and allocation system based on talent assessment can collect data in multiple dimensions and in multiple ways for different types of enterprises, accumulate time series data, store and migrate large-scale structured and unstructured data, and combine the Johari theory in the field of human resource organization management with intelligent analysis and statistical machine learning for data analysis and modeling, ultimately realizing configurable data visualization charts, data statistical learning reports, and capability assessment reports of different granularities.

[0030] 2. This human resource optimization and allocation system based on talent assessment builds a large-scale talent database by collecting and storing information on different types of employees, uses statistical machine learning modeling to perform data analysis and decision-making recommendations, and provides organizational management decision support for different roles through visual display. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is a schematic diagram of system connection of the present invention;

[0032] Figure 2is a schematic diagram of a processing unit of the present invention;

[0033] Figure 3 This is a schematic diagram of the specific operation flow of the evaluation of the human resources optimization configuration system of the present invention. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0035] See Figure 1-3 , the present invention provides the following three technical solutions:

[0036] The first implementation mode: a human resource optimization configuration system based on talent assessment, comprising a server, a processing unit and a client;

[0037] The server is configured as a platform for managing enterprise user accounts, assessment activity reports and data storage. The server includes enterprise user login, system maintenance, generation of assessment reports, user information maintenance and historical data storage.

[0038] The processing unit includes a data acquisition module, a data management module, a data analysis module, an evaluation unit, a display module, a feature extraction module and a feature database.

[0039] The data acquisition module is used to acquire data uploaded by customers and user public data downloaded by the big data center, and includes: a data collection module and a data storage module, wherein the data collection module is used to collect employee information through multiple dimensions according to the ability evaluation indicators of enterprise talents and organizations to obtain multi-dimensional collected data of enterprise employees; the data storage module is used to store the multi-dimensional collected data of enterprise employees collected by the data collection unit in a structured and on-demand unstructured manner.

[0040] The data acquisition module may also include a data update module, which is used to perform regular checks and update settings on the database, search for the latest data in real time, and perform persistent storage during the process of updating the database.

[0041] That is to say, the data acquisition module can be divided into three modules: data collection, data storage, and data update. Among them, the data collection module supports different methods such as PC and terminal instant messaging applications for data collection. The collected indicators include but are not limited to synergy, innovative spirit, active pressure bearing, service awareness, teamwork, professional ability, etc. The evaluation indicators can be flexibly set and have sufficient flexibility. At the same time, it can flexibly collect data from different types of employees in subordinates, superiors, and peers in three dimensions of employee skills, cognition, and character. Skills mainly examine the abilities and technologies possessed by employees in response to the business and needs of the enterprise department, as well as skills with higher difficulty coefficients including imagination, observation, theoretical generalization, and logical thinking to quickly discover and solve problems; cognition mainly examines employees' cultural quality, solid basic knowledge, work experience, and deep understanding of the research field; character is mainly used to examine employees' integrity, professional ethics, rigorous work style, strong willpower and other qualities, and fully and flexibly collect employee information from different aspects of multiple dimensions.

[0042] The data storage module mainly realizes structured and on-demand unstructured data storage, and can realize functions such as collection, storage and retrieval for continuous data. It can accumulate time series data for the overall organization, and can support functional requirements such as data migration in the process of building large-scale databases for talents, and support the use of historical data and the reference of historical results.

[0043] In the embodiment of the present application, in order to grasp the real-time data of employees in the enterprise department, to be able to perform data analysis based on the latest data, and to improve the accurate and rapid decision-making ability of organizational management, it is necessary to update the stored data, regularly start automatic data collection, automatic modeling, provide and push evaluation reports and other functions, and update the system data in time. The data update module searches for the latest data in real time by regularly checking and updating the database, and performs persistent storage during the process of updating the database.

[0044] The data management module is used to collect employee information through multiple dimensions based on the basic information uploaded by the user, the public data downloaded by the big data center, and the result data of the evaluation, so as to obtain multi-dimensional collected data of the enterprise employees, wherein, in the embodiment of the present application, the multiple dimensions include: at least two of skills, cognition, and character. As an example, the multiple dimensions may include: skills, cognition, and character. Among them, skills mainly examine the abilities and techniques possessed by employees for the business and needs of the enterprise department, as well as skills with higher difficulty coefficients including imagination, observation, theoretical generalization, and logical thinking to quickly discover and solve problems; cognition mainly examines the cultural quality of employees, solid basic knowledge, work experience, and deep understanding of the research field; character is mainly used to examine the qualities of employees such as integrity, professional ethics, rigorous work style, and strong willpower.

[0045] The data analysis module performs cluster analysis, classification analysis and outlier analysis on the multi-dimensional collected data of the enterprise employees based on machine learning technology to obtain data analysis results. As an example, the data analysis module uses a clustering algorithm to classify the enterprise employees into group categories based on the multi-dimensional collected data of the enterprise employees to obtain group categories of the enterprise employees.

[0046] The evaluation unit is used to generate test questions and test papers and evaluate the results;

[0047] The evaluation unit includes a question bank maintenance module, a question classification module, a question import module and a test paper evaluation module;

[0048] The question bank maintenance module is used to query the question category, question source, question difficulty information, add and modify question description (single choice, multiple choice, short answer), question classification, answer, question difficulty, question status (enabled, disabled), question category information

[0049] The test question classification module is used to classify the test questions in the test question bank according to the user's position, combine the examination direction of the questions in the test question bank, and automatically generate the evaluation test paper according to the test question composition strategy;

[0050] The test question importing module is used to import the assessment test papers into the system;

[0051] The test paper evaluation module uses a big data analysis engine to perform relevant operations on statistical indicators based on the test paper composition strategy, generates a statistical report based on the calculation results, and generates corresponding suggestions.

[0052] The display module generates configurable data visualization charts, visualization analysis reports and capability assessment reports, and visually displays the data visualization charts, visualization analysis reports and capability assessment reports;

[0053] The feature extraction module is used to extract the identity information of the person being evaluated and the associated work element features;

[0054] The feature database is used to store user feature data.

[0055] The client serves as a platform for information interaction between users and the system, and mainly includes an account login module and a data upload module.

[0056] The system also includes a log module for generating a work log, which includes at least progress dates, processing content corresponding to each date, problems encountered and planned solutions;

[0057] The log module is provided with a log filling module, and the work log filling module includes a progress date selection module, a processing content filling module, a problem to be solved filling module and a planned solution filling module.

[0058] The system also includes a warning reminder module, which is used to issue a reminder notification when the evaluation unit cannot be started or cannot perform comparative analysis on the key information extracted by the feature extraction module.

[0059] Second implementation method: In some embodiments of the present application, when a new employee collects data and joins, the data analysis module evaluates and classifies the individual capabilities of the employee based on a nonlinear SVM model to obtain a classification analysis result of the employee.

[0060] In an embodiment of the present application, the data analysis module performs an outlier point analysis on the multi-dimensional collected data of enterprise employees based on an index-based outlier point detection method to identify anomalies in the employee collected data.

[0061] For example, the data analysis module can cluster, classify and analyze the multi-dimensional data collected by different types of employees in three dimensions: outliers. Among them, for cluster analysis, this application can divide the types of human resource communication management groups into four categories: open, authoritarian, closed, and passive based on the Johari framework model, and use the clustering algorithm to divide the employees of the enterprise department into groups based on the personal overall evaluation data of the enterprise employees. The type distribution of employees in the department is used to understand the strengths and weaknesses of the organization and the characteristics of the current organization, and the organization is divided into three different types: unknown, potential, and efficient. If the employees of the organization are mostly closed, it means that the organization has great limitations in its understanding of the capabilities of employees, and cannot give full play to the potential capabilities of talents and improve organizational management; if the distribution of authoritarian and passive employees accounts for a large proportion, it means that the organization has a lot of room for improvement, and managers should fully tap the blind spots of employees and their blind spots; efficient organizations have been able to basically grasp the personality characteristics of employees, promote team collaboration, and effectively avoid conflicts. They can open organizational management plans to provide management opinions for other departments.

[0062] For example, taking the K-means clustering algorithm as an example, four data points are selected as the center of each cluster in the scenario of this application. Each data point is traversed in turn, and the following operations are performed each time (assuming that the currently traversed data point is Di): 1) Calculate the cluster center closest to Di and assign Di to this cluster; 2) Update the cluster center immediately (in fact, among all 4 clusters, only this cluster needs to update the cluster center); 3) Loop through the first two steps until the cluster center no longer changes position (at this time, the cluster to which this data point belongs is actually fixed); traverse all data points, complete clustering, and finally divide all personnel collected data into four clusters. As an example, this application can use a variety of clustering algorithms for data analysis, with flexible algorithm portability.

[0063] For classification analysis, when a new employee collects data and joins, the data analysis module 140 can evaluate and classify the individual talents' individual abilities and divide them into four categories: privacy, publicity, blind spots, and potential. The employee type is predicted through the classification algorithm. At the same time, a nonlinear SVM model is introduced to predict the future ability distribution of employees, providing decision-making suggestions for the department's organizational management and talent training. It should be noted that the application scenario of the present application belongs to a nonlinear problem. For linearly inseparable samples, the SVM maps the samples from the inseparable space to the separable space through spatial mapping. SVM introduces a kernel function to convert the inner product of the mapped high-dimensional space into a function of the low-dimensional space, where Φ is a mapping from a low-dimensional feature space to a high-dimensional feature space. If there is a function K(x,z), for any low-dimensional feature vectors x and z, there are:

[0064]

[0065] The function K(x,z) is called the kernel function.

[0066] Available kernel functions include polynomial kernel functions:

[0067] K(x,z)=(yx*z+r) d ;

[0068] Among them, y, r, and d are hyperparameters;

[0069] Available kernel functions also include Gaussian kernel functions:

[0070]

[0071] Among them, σ is the only hyperparameter, ||xy|| represents the norm of the vector, that is, the modulus of the vector;

[0072] Substituting the kernel function into the objective function of the generalized SVM learning algorithm, we get the optimization problem of nonlinear SVM, where the data set j is:

[0073] T={(x1,y1),(x2,y2),…(x n ,y n )},x i ∈x=R n ,y i ∈y={-1, +1}, i=1,2,…,N:

[0074]

[0075]

[0076] 0≤α i ≤C, i=1,2,...,N;

[0077] The optimal solution can be obtained Select α * A positive component of 0< calculate:

[0078]

[0079] Construct a decision function:

[0080]

[0081] Using the prediction results of the nonlinear SVM algorithm, a multi-dimensional comparative analysis of the ability distribution of employees is conducted to provide scientific and digital management suggestions for organizational managers.

[0082] For outlier analysis, in the process of large-scale data analysis, there will be a small number of data objects that are inconsistent with the general behavior or characteristics of the data. These data objects are called outliers. After identifying the outliers, we are committed to finding implicit models between abnormal data through abnormal data mining for intelligent analysis and prediction. By studying abnormal data, we can find effective organizational management methods and strategies suitable for human resources in enterprise departments. In an embodiment of the present application, the data analysis module can use index-based outlier detection. Based on the data collected by the data management module, a multidimensional index structure R-tree or kd tree is used to find the neighbors of each object within a radius of d. Assume that M is the maximum number of objects in the d field of the outlier data. If M+l neighbors of object S are found, object O is not an outlier, so as to identify the abnormal situation of employee data collection and conduct in-depth analysis on it.

[0083] The third implementation method: The specific operation steps of evaluating the above-mentioned human resource optimization allocation system include:

[0084] Step 1: The system imports the accumulated question bank into the system based on the previous assessment experience; for a specific job competency evaluation process, it is also necessary to organize professional skill questions and import them into the question bank before the assessment;

[0085] Step 2: The system compiles the test papers according to the results of competency analysis, the weights of various factors in the competency model, and the examination directions of the questions in the question bank. The system automatically generates the evaluation test papers according to the test composition strategy.

[0086] Step 3: The person being assessed logs into the assessment system and undergoes competency assessment;

[0087] Step 4: The system uses the big data analysis engine to perform relevant operations on the statistical indicators based on the test paper composition strategy, generates a statistical report based on the calculation results, and generates corresponding suggestions;

[0088] Step 5: System administrators can download the evaluation report. The system also provides an overall evaluation report for the entire organization or department.

[0089] Step 6: After the scoring is completed, the evaluator can log in to the system to obtain his or her own evaluation report. The system also provides an overall evaluation report for the entire organization or department.

[0090] Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art, and the model parameters of each electrical appliance are not specifically limited, and conventional equipment can be used.

[0091] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0092] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A human resource optimization configuration system based on talent assessment, characterized in that: Includes server, processing unit and client; The server is configured as a platform for managing enterprise user accounts, assessment activity reports and data storage; The processing unit includes a data acquisition module, a data management module, a data analysis module, an evaluation unit, a display module, a feature extraction module and a feature database; The client serves as a platform for information interaction between users and the system, and mainly includes an account login module and a data upload module.

2. The human resource optimization configuration system based on talent assessment according to claim 1, characterized in that: The server includes enterprise user login, system maintenance, evaluation report generation, user information maintenance and historical data storage.

3. The human resource optimization configuration system based on talent assessment according to claim 1 is characterized by: The data acquisition module is used to acquire data uploaded by customers and user public data downloaded by the big data center; The evaluation unit is used to generate test questions and test papers and evaluate the results; The data management module is used to collect employee information in multiple dimensions based on the basic information uploaded by the user, the public data downloaded by the big data center, and the evaluation result data, so as to obtain multi-dimensional collected data of enterprise employees; The data analysis module performs cluster analysis, classification analysis and outlier analysis on the multi-dimensional collected data of the enterprise employees based on machine learning technology to obtain data analysis results; The display module generates configurable data visualization charts, visualization analysis reports and capability assessment reports, and visually displays the data visualization charts, visualization analysis reports and capability assessment reports; The feature extraction module is used to extract the identity information of the person being evaluated and the associated work element features; The feature database is used to store user feature data.

4. The human resource optimization configuration system based on talent assessment according to claim 1 is characterized by: The evaluation unit includes a question bank maintenance module, a question classification module, a question import module and a test paper evaluation module.

5. The human resource optimization configuration system based on talent assessment according to claim 4 is characterized by: The question bank maintenance module is used to query the question category, question source, question difficulty information, add and modify question description (single choice, multiple choice, short answer), question classification, answer, question difficulty, question status (enabled, disabled), question category information The test question classification module is used to classify the test questions in the test question bank according to the user's position, combine the examination direction of the questions in the test question bank, and automatically generate the evaluation test paper according to the test question composition strategy; The test question importing module is used to import the assessment test papers into the system; The test paper evaluation module uses a big data analysis engine to perform relevant operations on statistical indicators based on the test paper composition strategy, generates a statistical report based on the calculation results, and generates corresponding suggestions.

6. The human resource optimization configuration system based on talent assessment according to claim 1 is characterized by: The system also includes a log module for generating a work log, which at least includes progress dates, processing content corresponding to each date, problems encountered and planned solutions.

7. The human resource optimization configuration system based on talent assessment according to claim 6 is characterized by: The log module is provided with a log filling module, and the work log filling module includes a progress date selection module, a processing content filling module, a problem to be solved filling module and a planned solution filling module.

8. The human resource optimization configuration system based on talent assessment according to claim 1 is characterized by: The system also includes a warning reminder module, which is used to issue a reminder notification when the evaluation unit cannot be started or cannot perform comparative analysis on the key information extracted by the feature extraction module.

Images